[EPLB]Record expert map without dynamic eplb. (#3409)

What this PR does / why we need it?
1.Record expert map without dynamic eplb.
2.Add export PYTHONOPTIMIZE=1  when using dynamic eplb.
3.change eplb doc

Does this PR introduce any user-facing change?
How was this patch tested?
Qwen3_moe in A3.

- vLLM version: v0.11.0

---------

Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>

vllm_ascend/quantization/w4a8_dynamic.py

@@ -140,7 +140,8 @@ class AscendW4A8DynamicFusedMoEMethod:
         # NOTE: new quantize weights: 2 int4 pack into int8
         self.new_quant_version = quant_version == "1.0.0"
         self.tp_size = 1 if vllm_config.parallel_config.enable_expert_parallel else self.ep_group.world_size
-        self.dynamic_eplb = get_ascend_config().dynamic_eplb
+        ascend_config = get_ascend_config()
+        self.dynamic_eplb = ascend_config.dynamic_eplb or ascend_config.expert_map_record_path
         if self.new_quant_version and self.tp_size > 16:
             raise ValueError(
                 "The current weight does not support moe part tp>16.")

vllm_ascend/quantization/w8a8_dynamic.py

@@ -124,7 +124,7 @@ class AscendW8A8DynamicFusedMoEMethod:
             vllm_config.compilation_config.level == CompilationLevel.PIECEWISE
             and not vllm_config.model_config.enforce_eager
             and not ascend_config.torchair_graph_config.enabled)
-        self.dynamic_eplb = ascend_config.dynamic_eplb
+        self.dynamic_eplb = ascend_config.dynamic_eplb or ascend_config.expert_map_record_path
 
         try:
             device_group = get_mc2_group().device_group